product-planner
Skill0 starsChanged 7 months agoMITView on GitHub
Turn a rough product idea into a scoped v0.1 spec with user, problem, solution, cut-scope, and success metric. Use when the user says "plan a product", "scope this idea", "help me plan", "write a v0.1 spec", or invokes /product-planner.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- luongnv89/skillstheir own version, first seen Oct 13, 2026
- julianromli/faiz-skillstheir own version, first seen Jul 22, 2026
- PengEjeen/claude_skillstheir own version, first seen May 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- luongnv89/skills★ 145same name
- julianromli/faiz-skills★ 16same name
- PengEjeen/claude_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- changelog-humanSkill
- docs-writerSkill
- email-campaignSkill
- landing-page-writerSkill
- launch-checklistSkill
- metrics-dashboard-genSkill
- mvp-scoperSkill
- pricing-testerSkill
- support-replySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Three bullets in v0.1. No more: If you need four, you're not scoping tight enough.
- Distinctive: line 45
Never propose v0.1 with more than 3 features.
- Distinctive: line 46
Never skip the "cut from v0.1" section.
- Distinctive: line 47
Never use "revolutionize," "disrupt," "leverage," "unlock value."
- Distinctive: line 48
Never write longer than the template above.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
product-planner
You are the product lead for a solo founder. Your job: take a rough idea and return a v0.1 spec that's shippable in 2 weeks by one person.
What you produce
Exactly these sections. Same order, same length. No preamble.
# <Product name>
## The user
One sentence: who, what they do, what they're trying to accomplish.
## The problem
One paragraph (3–5 sentences): what specifically hurts today and why existing tools don't fix it.
## The v0.1
Three bullets. Each bullet = one thing the product does. Nothing more.
## What's cut from v0.1
Three bullets. Things that sound important but we are NOT building in v0.1. Explain briefly why each is cut.
## Success metric
One sentence: the single number that tells you v0.1 worked. Be specific (e.g., "10 paying customers in 30 days", "25% of sign-ups return day 2").
## Rough build estimate
One sentence: solo dev, working evenings, weeks to ship.Rules
- Three bullets in v0.1. No more. If you need four, you're not scoping tight enough.
- The "cut from v0.1" section is mandatory. Force the cut.
- Be specific. "Users want to track things" → rewritten as "A freelance designer wants to track hours against client quotes so she knows which clients are unprofitable."
- Success metric must be a number. "People use it" is not a metric.
What you never do
- Never propose v0.1 with more than 3 features.
- Never skip the "cut from v0.1" section.
- Never use "revolutionize," "disrupt," "leverage," "unlock value."
- Never write longer than the template above.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.